<p>In <a href="https://github.com/mlpack/mlpack/pull/696#discussion_r67194489">src/mlpack/methods/edge_boxes/feature_extraction_impl.hpp</a>:</p>
<pre style='color:#555'>> +
> + this->Gradient(OutImage, Magnitude, Orientation);
> +
> + size_t downscale = std::max(1, (int)(shrink * scale));
> +
> + CubeType Hist = this->Histogram(Magnitude, Orientation,
> + downscale, 0);
> +
> + channels.slice(slice_idx) =
> + bilinearInterpolation( Magnitude, rsize, csize);
> + slice_idx++;
> + for(size_t i = 0; i < InImage.n_slices; ++i)
> + channels.slice(i + slice_idx) =
> + bilinearInterpolation( Magnitude, rsize, csize);
> + slice_idx += 3;
> + scale += 0.5;
</pre>
<p>I would recommend to use <code>slice_idx += n_slices</code>instead of <code>slice_idx += 3;</code> there is no guarantee that we call the function with a 3 channel image.</p>
<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">—<br />You are receiving this because you are subscribed to this thread.<br />Reply to this email directly, <a href="https://github.com/mlpack/mlpack/pull/696/files/b38b688edfc4c2ee8bf461240f8384a70575d3a4#r67194489">view it on GitHub</a>, or <a href="https://github.com/notifications/unsubscribe/AJ4bFIGEjUCSB-ZS11X3iN1ozGQrxJRnks5qMCVqgaJpZM4I1lnr">mute the thread</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFColax3bApQ8y2yQTrpLOCNW63znks5qMCVqgaJpZM4I1lnr.gif" width="1" /></p>
<div itemscope itemtype="http://schema.org/EmailMessage">
<div itemprop="action" itemscope itemtype="http://schema.org/ViewAction">
<link itemprop="url" href="https://github.com/mlpack/mlpack/pull/696/files/b38b688edfc4c2ee8bf461240f8384a70575d3a4#r67194489"></link>
<meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>